summaryrefslogtreecommitdiff
path: root/git/test/performance/test_streams.py
diff options
context:
space:
mode:
authorSebastian Thiel <byronimo@gmail.com>2014-11-17 10:14:43 +0100
committerSebastian Thiel <byronimo@gmail.com>2014-11-17 10:14:43 +0100
commite4d8fb73daa82420bdc69c37f0d58f7cb4cd505a (patch)
tree38e1241fd6d756f783b6b56dc6628ac3ca41ed4f /git/test/performance/test_streams.py
parent7aba59a2609ec768d5d495dafd23a4bce8179741 (diff)
parentc8e70749887370a99adeda972cc3503397b5f9a7 (diff)
downloadgitpython-e4d8fb73daa82420bdc69c37f0d58f7cb4cd505a.tar.gz
Merge pull request #204 from hashar/pep8-linting
Pep8 linting
Diffstat (limited to 'git/test/performance/test_streams.py')
-rw-r--r--git/test/performance/test_streams.py56
1 files changed, 26 insertions, 30 deletions
diff --git a/git/test/performance/test_streams.py b/git/test/performance/test_streams.py
index 93e88841..e42867a3 100644
--- a/git/test/performance/test_streams.py
+++ b/git/test/performance/test_streams.py
@@ -18,16 +18,16 @@ from lib import (
class TestObjDBPerformance(TestBigRepoR):
-
- large_data_size_bytes = 1000*1000*10 # some MiB should do it
- moderate_data_size_bytes = 1000*1000*1 # just 1 MiB
-
+
+ large_data_size_bytes = 1000 * 1000 * 10 # some MiB should do it
+ moderate_data_size_bytes = 1000 * 1000 * 1 # just 1 MiB
+
@with_rw_repo('HEAD', bare=True)
def test_large_data_streaming(self, rwrepo):
# TODO: This part overlaps with the same file in gitdb.test.performance.test_stream
# It should be shared if possible
ldb = LooseObjectDB(os.path.join(rwrepo.git_dir, 'objects'))
-
+
for randomize in range(2):
desc = (randomize and 'random ') or ''
print >> sys.stderr, "Creating %s data ..." % desc
@@ -35,32 +35,30 @@ class TestObjDBPerformance(TestBigRepoR):
size, stream = make_memory_file(self.large_data_size_bytes, randomize)
elapsed = time() - st
print >> sys.stderr, "Done (in %f s)" % elapsed
-
- # writing - due to the compression it will seem faster than it is
+
+ # writing - due to the compression it will seem faster than it is
st = time()
binsha = ldb.store(IStream('blob', size, stream)).binsha
elapsed_add = time() - st
assert ldb.has_object(binsha)
db_file = ldb.readable_db_object_path(bin_to_hex(binsha))
fsize_kib = os.path.getsize(db_file) / 1000
-
-
+
size_kib = size / 1000
print >> sys.stderr, "Added %i KiB (filesize = %i KiB) of %s data to loose odb in %f s ( %f Write KiB / s)" % (size_kib, fsize_kib, desc, elapsed_add, size_kib / elapsed_add)
-
+
# reading all at once
st = time()
ostream = ldb.stream(binsha)
shadata = ostream.read()
elapsed_readall = time() - st
-
+
stream.seek(0)
assert shadata == stream.getvalue()
print >> sys.stderr, "Read %i KiB of %s data at once from loose odb in %f s ( %f Read KiB / s)" % (size_kib, desc, elapsed_readall, size_kib / elapsed_readall)
-
-
+
# reading in chunks of 1 MiB
- cs = 512*1000
+ cs = 512 * 1000
chunks = list()
st = time()
ostream = ldb.stream(binsha)
@@ -71,21 +69,21 @@ class TestObjDBPerformance(TestBigRepoR):
break
# END read in chunks
elapsed_readchunks = time() - st
-
+
stream.seek(0)
assert ''.join(chunks) == stream.getvalue()
-
+
cs_kib = cs / 1000
print >> sys.stderr, "Read %i KiB of %s data in %i KiB chunks from loose odb in %f s ( %f Read KiB / s)" % (size_kib, desc, cs_kib, elapsed_readchunks, size_kib / elapsed_readchunks)
-
+
# del db file so git has something to do
os.remove(db_file)
-
- # VS. CGIT
+
+ # VS. CGIT
##########
# CGIT ! Can using the cgit programs be faster ?
proc = rwrepo.git.hash_object('-w', '--stdin', as_process=True, istream=subprocess.PIPE)
-
+
# write file - pump everything in at once to be a fast as possible
data = stream.getvalue() # cache it
st = time()
@@ -96,25 +94,23 @@ class TestObjDBPerformance(TestBigRepoR):
gelapsed_add = time() - st
del(data)
assert gitsha == bin_to_hex(binsha) # we do it the same way, right ?
-
+
# as its the same sha, we reuse our path
fsize_kib = os.path.getsize(db_file) / 1000
print >> sys.stderr, "Added %i KiB (filesize = %i KiB) of %s data to using git-hash-object in %f s ( %f Write KiB / s)" % (size_kib, fsize_kib, desc, gelapsed_add, size_kib / gelapsed_add)
-
- # compare ...
+
+ # compare ...
print >> sys.stderr, "Git-Python is %f %% faster than git when adding big %s files" % (100.0 - (elapsed_add / gelapsed_add) * 100, desc)
-
-
+
# read all
st = time()
s, t, size, data = rwrepo.git.get_object_data(gitsha)
gelapsed_readall = time() - st
print >> sys.stderr, "Read %i KiB of %s data at once using git-cat-file in %f s ( %f Read KiB / s)" % (size_kib, desc, gelapsed_readall, size_kib / gelapsed_readall)
- # compare
+ # compare
print >> sys.stderr, "Git-Python is %f %% faster than git when reading big %sfiles" % (100.0 - (elapsed_readall / gelapsed_readall) * 100, desc)
-
-
+
# read chunks
st = time()
s, t, size, stream = rwrepo.git.stream_object_data(gitsha)
@@ -125,7 +121,7 @@ class TestObjDBPerformance(TestBigRepoR):
# END read stream
gelapsed_readchunks = time() - st
print >> sys.stderr, "Read %i KiB of %s data in %i KiB chunks from git-cat-file in %f s ( %f Read KiB / s)" % (size_kib, desc, cs_kib, gelapsed_readchunks, size_kib / gelapsed_readchunks)
-
- # compare
+
+ # compare
print >> sys.stderr, "Git-Python is %f %% faster than git when reading big %s files in chunks" % (100.0 - (elapsed_readchunks / gelapsed_readchunks) * 100, desc)
# END for each randomization factor